Informational parsimony – i.e., using the minimal information required f...
Learning policies from fixed offline datasets is a key challenge to scal...
Several self-supervised representation learning methods have been propos...
Offline reinforcement learning (RL) struggles in environments with rich ...
Goal-conditioned reinforcement learning (RL) is a promising direction fo...
Learning to control an agent from data collected offline in a rich
pixel...
A person walking along a city street who tries to model all aspects of t...
We hypothesize that empirically studying the sample complexity of offlin...
Entropy regularization is used to get improved optimization performance ...
We study the problem of off-policy critic evaluation in several variants...
The policy gradient theorem is defined based on an objective with respec...
Off-policy deep reinforcement learning (RL) algorithms are incapable of
...
Exploration and adaptation to new tasks in a transfer learning setup is ...
A central challenge in reinforcement learning is discovering effective
p...
Deep reinforcement learning is the combination of reinforcement learning...
Online, off-policy reinforcement learning algorithms are able to use an
...
We introduce a deep generative model for functions. Our model provides a...
We investigate the use of alternative divergences to Kullback-Leibler (K...
We propose Bayesian hypernetworks: a framework for approximate Bayesian
...
In recent years, significant progress has been made in solving challengi...
Even though active learning forms an important pillar of machine learnin...